Naga Dheeraj Kurapati
M.S. Electrical Engineering Candidate
EE798 project topic: Roadway image segmentation for calculating Post Encroachment Time
Soumya Konery Satheeshkumar
M.S. Electrical Engineering Candidate
Thesis topic: Detection of heat stress in plants using machine learning regression models
James Bunnell
M.S. Electrical Engineering Candidate
Thesis topic: Machine- and Deep-Learning Architectures for Classifying 2D and 3D Material Interaction in Novel Semiconductor Devices
Deeksha Kondi Udayashankar
M.S. Electrical Engineering Graduate (graduated summer 2023)
Thesis topic: Sampling Acceleration and Orientation using SPI between the iCE40UP FPGA and the LSM6DSOX IMU for in situ Fall Detection and Classification
Jingxiao Tian
PhD Electrical Engineering Candidate
Research focus: Fall Prediction and Detection in At-Risk Older Adults through Inferencing at the Edge
Lab hours: Monday – Friday, 11:00AM to 4:00PM
Shreyas Narasimhiah Ramesh
M.S. Electrical Engineering Candidate
Research focus: Embedded Anchor-to-Joint (A2J) Pose Estimation from Depth Images on the Xilinx Kria KV260 Vision AI board
Lab hours: Monday – Friday, 11:00AM to 4:00PM
Priyanka Partane
M.S. Electrical Engineering Graduate (graduated spring 2022)
EE798 project topic: Line-speed Packet Capture and Feature Extraction for Training Asymmetric Stacked Autoencoders for Network Anomaly Detection
Vineet Kandunuri
M.S. Electrical Engineering Candidate
Thesis topic: MIST: A Machine Intelligent Sensor Topology Fog Computing Architecture to Mitigate the Propagation of Cascading Power Outages
- Vineet Kandunuri, Mahasweta Sarkar, and Christopher Paolini, Fog-compute capable smart metering infrastructure, IEEE International Conference on Advanced Networks and Telecommunications Systems, 13-16 December 2021, IDRBT, Hyderabad, India.
Veena Keeranagi
M.S. Electrical Engineering Graduate (graduated fall 2020)
EE798 project topic: Optimal LoRa Gateway Placement
Erfan Chowdhury Shourov
M.S. Electrical Engineering Graduate (graduated spring 2022)
Thesis topic: Deep Learning Architectures for Skateboarder-Pedestrian Surrogate Safety Measures
Publications:
- Shourov, C.E.; Sarkar, M.; Jahangiri, A.; Paolini, C. Deep Learning Architectures for Skateboarder-Pedestrian Surrogate Safety Measures. Future Transp. 2021, 1, 387-413. 10.3390/futuretransp1020022
- E. C. Shourov and C. Paolini, “Laying the Groundwork for Automated Computation of Surrogate Safety Measures (SSM) for Skateboarders and Pedestrians using Artificial Intelligence,” 2020 Third International Conference on Artificial Intelligence for Industries (AI4I), Irvine, CA, USA, 2020, pp. 19-22, doi: 10.1109/AI4I49448.2020.00011.
- C. E. Shourov and C. Paolini, “Skateboarder and Pedestrian Conflict Zone Detection Dataset,” 14-Nov-2020. [Online]. Available: osf.io/nyhf7, DOI 10.17605/OSF.IO/NYHF7.
- C. Paolini, C. E. Shourov, A. Jahangiri, and S. G. Machiani, “Skateboarder and Pedestrian Dataset,” 30-Jan-2020. [Online]. Available: osf.io/cqd9z, DOI 10.17605/OSF.IO/CQD9Z.
Ugur Emre Dogan
M.S. Electrical Engineering Graduate (graduated summer 2021)
EE798 project topic: On-device vehicle detection, classification, and tracking for Surrogate Safety Measures
Arya Yazdani
M.S. Electrical Engineering Graduate (graduated summer 2021)
EE798 project topic: Edge computing vision architectures for Surrogate Safety Measurements
Report: Real-time vehicle and pedestrian object detection and classification on the Coral EdgeTPU Board for Surrogate Safety Measurements
Jared Brzenski
Computational Science PhD Candidate
Jared is supported under NSF Office of Advanced Cyberinfrastructure (OAC) CC* Storage Grant 1659169 Implementation of a Distributed, Shareable, and Parallel Storage Resource at San Diego State University to Facilitate High-Performance Computing for Climate Science. The goals and objectives of the project will be to implement parallel shared-file I/O capabilities (i.e. each process performs I/O to a single file which is shared) in our Geologic CO2 Sequestration and Coastal Ocean Modeling applications, at multiple layers, using (1) parallel I/O libraries (HDF5, Parallel netCDF), (2) a middleware layer (MPI-IO), and a parallel file system (BeeGFS). Publications:
- Brzenski, J., Paolini, C., and Castillo, J. E., Improving the I/O of Large Geophysical Models using PnetCDF and BeeGFS, Parallel Computing, 2021, ISSN 0167-8191, 10.1016/j.parco.2021.102786
Christopher Johnson
Computer Engineering Undergraduate
Undergraduate research project: Advanced Persistent Threat (APT) Detection. Packet capture and inspection using the Xilinx U250 Alveo Data Center accelerator card on the UC San Diego / UC Berkeley PRP Kubernetes cluster.